428 S Shaw LN
East Lansing, Michigan
United States of America
I am Yihua Zhang (张逸骅), a second-year Ph.D. student from OPTML Group at Michigan State University, supervised by Prof. Sijia Liu. My research focuses on the trustworthy and scalable ML algorithms. In general, my research spans the areas of machine learning (ML)/deep learning (DL), optimization theory, computer vision, and security. These research topics provide a solid foundation for my current and future research: Making AI system responsible and efficient. My research on these two goals are intervened and can be summarized as the following two perspectives:
Algorithmic perspective: This line of research designs the scalable and theoretically-grounded machine learning algorithms subject to real-life constraints, e.g., computation/communication overhead, robustness, fairness, and interpretability.
Application perspective: This line of research tackles the domain-specific challenges to achieve scalable and trustworthy AI, e.g., robustness enhancement, fairness promotion, data privacy protection, and model compression.
|Oct 20, 2023||Grateful to be awarded the NeurIPS 2023 Scholar Award !|
|Sep 22, 2023||One first-authored papers accepted in NeurIPS 2023! Paper and codes will come soon!|
|Aug 3, 2023||Our survey paper An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning has been made public on arxiv!|
|Jul 13, 2023||One first-authored paper accepted by ICCV’23!|
|May 19, 2023||I am honored to be selected to be the CVPR 2023 Outstanding Reviewer (232/7000+)!|
See a full publication list at here.
preprintAn Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine LearningIn arxiv 2308.00788 Aug 2023
NeurIPS’23Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer LearningIn Thirty-seventh Conference on Neural Information Processing Systems Aug 2023
ICCV’23Robust Mixture-of-Expert Training for Convolutional Neural NetworksIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Oct 2023
ICLR’23What Is Missing in IRM Training and Evaluation? Challenges and SolutionsIn Eleventh International Conference on Learning Representations Oct 2023
NeurIPS’22Advancing Model Pruning via Bi-level OptimizationIn Thirty-sixth Conference on Neural Information Processing Systems Oct 2022
NeurIPS’22Fairness ReprogrammingIn Thirty-sixth Conference on Neural Information Processing Systems Oct 2022
ICML’22Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level OptimizationIn Proceedings of the 39th International Conference on Machine Learning Oct 2022
CVPR’22Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for FreeIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Oct 2022